I try to understand why most researchers are using GA for mobile robot path planning. In the Paper Path Planning for the Mobile Robot: A Review it shows its the most used. In the paper A Review of Optimization Algorithms for University Timetable Scheduling. They write that "GAs are particularly applied to complex optimization problems, which are challenges that have different parameters or characteristics that need to be combined in search of the best solution and, at the same time, cannot be represented mathematically"
That document claims
The results shows GA, PSO, APF, and ACO are the most used four approaches to solve the path planning of mobile robot.
The survey shows GA (genetic algorithm), PSO (particle swarm optimization algorithm), APF (artificial potential field), and ACO (ant colony optimization algorithm) are the most used approaches to solve the path planning of mobile robot
Which are both extremely suspect to me and given without evidence or a citation. Given the journal it is published in isn't even an engineering journal, let alone a robotics journal, I'm suspicious of anything written in that document that I don't already know is true. The author throws up a terrible straw man argument against search-based planners and suffocates other methods with only 1-3 sentences of lip service or ignores important methods like RRT and Navigation Functions.
I can say from personal experience at several robotics companies that I've never seen a GA algorithm being used for path planning across many domains of robotics. Its not to say they don't have their niche, but that niche is not the usual use-case. Traditional search and sampling based planners can yield high quality results in a fraction of the listed times in the GA papers and are widely seen across mobile, manipulation, and AUV navigation systems.
I believe this document is misleading and in many ways just factually incorrect, or at least inadequate.
Well, mobile robot path planning is a complex optimization problem, a challenge that has different parameters or characteristics that need to be combined in search of the best solution and, at the same time, cannot be represented mathematically.
Seems to me that makes the genetic algorithm approach worth exploring for a given application, although I'd want to see the citation for it being "the most used". If you need to get into detail about the parameters, characteristics, and what to optimize, you're getting into Ben's book.